{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KOYGBMPNQ4DITAAQNGV4AI5XG5","short_pith_number":"pith:KOYGBMPN","schema_version":"1.0","canonical_sha256":"53b060b1ed870689801069abc023b73755c1e0b306e0ef28b9473bd46d1133f7","source":{"kind":"arxiv","id":"2504.19384","version":1},"attestation_state":"computed","paper":{"title":"From Inductive to Deductive: LLMs-Based Qualitative Data Analysis in Requirements Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ann Barcomb, Mohamad Hussein, Mohammad Moshirpour, Syed Tauhid Ullah Shah","submitted_at":"2025-04-27T23:21:52Z","abstract_excerpt":"Requirements Engineering (RE) is essential for developing complex and regulated software projects. Given the challenges in transforming stakeholder inputs into consistent software designs, Qualitative Data Analysis (QDA) provides a systematic approach to handling free-form data. However, traditional QDA methods are time-consuming and heavily reliant on manual effort. In this paper, we explore the use of Large Language Models (LLMs), including GPT-4, Mistral, and LLaMA-2, to improve QDA tasks in RE. Our study evaluates LLMs' performance in inductive (zero-shot) and deductive (one-shot, few-shot"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.19384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-04-27T23:21:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"feee0ae3964262d1645dffb6a8a3c6372a137db3cf4efbd2ace972312030b87f","abstract_canon_sha256":"fff614af2cd401d24c7211662b62a98d88706c87f09370a9f9186ade70df3a1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:56.416009Z","signature_b64":"mdi8KVDzzfHTnltTtPC+IlRIVT8j0ZeocSkMbV4lnw7OQ525UBTsWAKWheFGVhL3aX3c8GqqaWra9EqwGgTvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53b060b1ed870689801069abc023b73755c1e0b306e0ef28b9473bd46d1133f7","last_reissued_at":"2026-07-05T10:54:56.415528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:56.415528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Inductive to Deductive: LLMs-Based Qualitative Data Analysis in Requirements Engineering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ann Barcomb, Mohamad Hussein, Mohammad Moshirpour, Syed Tauhid Ullah Shah","submitted_at":"2025-04-27T23:21:52Z","abstract_excerpt":"Requirements Engineering (RE) is essential for developing complex and regulated software projects. Given the challenges in transforming stakeholder inputs into consistent software designs, Qualitative Data Analysis (QDA) provides a systematic approach to handling free-form data. However, traditional QDA methods are time-consuming and heavily reliant on manual effort. In this paper, we explore the use of Large Language Models (LLMs), including GPT-4, Mistral, and LLaMA-2, to improve QDA tasks in RE. Our study evaluates LLMs' performance in inductive (zero-shot) and deductive (one-shot, few-shot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19384","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.19384/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.19384","created_at":"2026-07-05T10:54:56.415590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.19384v1","created_at":"2026-07-05T10:54:56.415590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19384","created_at":"2026-07-05T10:54:56.415590+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOYGBMPNQ4DI","created_at":"2026-07-05T10:54:56.415590+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOYGBMPNQ4DITAAQ","created_at":"2026-07-05T10:54:56.415590+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOYGBMPN","created_at":"2026-07-05T10:54:56.415590+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOYGBMPNQ4DITAAQNGV4AI5XG5","json":"https://pith.science/pith/KOYGBMPNQ4DITAAQNGV4AI5XG5.json","graph_json":"https://pith.science/api/pith-number/KOYGBMPNQ4DITAAQNGV4AI5XG5/graph.json","events_json":"https://pith.science/api/pith-number/KOYGBMPNQ4DITAAQNGV4AI5XG5/events.json","paper":"https://pith.science/paper/KOYGBMPN"},"agent_actions":{"view_html":"https://pith.science/pith/KOYGBMPNQ4DITAAQNGV4AI5XG5","download_json":"https://pith.science/pith/KOYGBMPNQ4DITAAQNGV4AI5XG5.json","view_paper":"https://pith.science/paper/KOYGBMPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.19384&json=true","fetch_graph":"https://pith.science/api/pith-number/KOYGBMPNQ4DITAAQNGV4AI5XG5/graph.json","fetch_events":"https://pith.science/api/pith-number/KOYGBMPNQ4DITAAQNGV4AI5XG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOYGBMPNQ4DITAAQNGV4AI5XG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOYGBMPNQ4DITAAQNGV4AI5XG5/action/storage_attestation","attest_author":"https://pith.science/pith/KOYGBMPNQ4DITAAQNGV4AI5XG5/action/author_attestation","sign_citation":"https://pith.science/pith/KOYGBMPNQ4DITAAQNGV4AI5XG5/action/citation_signature","submit_replication":"https://pith.science/pith/KOYGBMPNQ4DITAAQNGV4AI5XG5/action/replication_record"}},"created_at":"2026-07-05T10:54:56.415590+00:00","updated_at":"2026-07-05T10:54:56.415590+00:00"}